Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles
The deep convolutional neural network has led the trend of vision-based road detection, however, obtaining a full road area despite the occlusion from monocular vision remains challenging due to the dynamic scenes in autonomous driving. Inferring the occluded road area requires a comprehensive under...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/21/4711 |
| _version_ | 1811301913863389184 |
|---|---|
| author | Kewei Wang Fuwu Yan Bin Zou Luqi Tang Quan Yuan Chen Lv |
| author_facet | Kewei Wang Fuwu Yan Bin Zou Luqi Tang Quan Yuan Chen Lv |
| author_sort | Kewei Wang |
| collection | DOAJ |
| description | The deep convolutional neural network has led the trend of vision-based road detection, however, obtaining a full road area despite the occlusion from monocular vision remains challenging due to the dynamic scenes in autonomous driving. Inferring the occluded road area requires a comprehensive understanding of the geometry and the semantics of the visible scene. To this end, we create a small but effective dataset based on the KITTI dataset named KITTI-OFRS (KITTI-occlusion-free road segmentation) dataset and propose a lightweight and efficient, fully convolutional neural network called OFRSNet (occlusion-free road segmentation network) that learns to predict occluded portions of the road in the semantic domain by looking around foreground objects and visible road layout. In particular, the global context module is used to build up the down-sampling and joint context up-sampling block in our network, which promotes the performance of the network. Moreover, a spatially-weighted cross-entropy loss is designed to significantly increases the accuracy of this task. Extensive experiments on different datasets verify the effectiveness of the proposed approach, and comparisons with current excellent methods show that the proposed method outperforms the baseline models by obtaining a better trade-off between accuracy and runtime, which makes our approach is able to be applied to autonomous vehicles in real-time. |
| first_indexed | 2024-04-13T07:18:34Z |
| format | Article |
| id | doaj.art-0433feb34ca2484190bc71da8438d149 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T07:18:34Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0433feb34ca2484190bc71da8438d1492022-12-22T02:56:40ZengMDPI AGSensors1424-82202019-10-011921471110.3390/s19214711s19214711Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous VehiclesKewei Wang0Fuwu Yan1Bin Zou2Luqi Tang3Quan Yuan4Chen Lv5Hubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, ChinaHubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, ChinaHubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, ChinaHubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, ChinaHubei Key Laboratory of Advanced Technology for Automotive Components, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Mechanical and Aerospace Engineering, Nanyang Technological University, 639798, SingaporeThe deep convolutional neural network has led the trend of vision-based road detection, however, obtaining a full road area despite the occlusion from monocular vision remains challenging due to the dynamic scenes in autonomous driving. Inferring the occluded road area requires a comprehensive understanding of the geometry and the semantics of the visible scene. To this end, we create a small but effective dataset based on the KITTI dataset named KITTI-OFRS (KITTI-occlusion-free road segmentation) dataset and propose a lightweight and efficient, fully convolutional neural network called OFRSNet (occlusion-free road segmentation network) that learns to predict occluded portions of the road in the semantic domain by looking around foreground objects and visible road layout. In particular, the global context module is used to build up the down-sampling and joint context up-sampling block in our network, which promotes the performance of the network. Moreover, a spatially-weighted cross-entropy loss is designed to significantly increases the accuracy of this task. Extensive experiments on different datasets verify the effectiveness of the proposed approach, and comparisons with current excellent methods show that the proposed method outperforms the baseline models by obtaining a better trade-off between accuracy and runtime, which makes our approach is able to be applied to autonomous vehicles in real-time.https://www.mdpi.com/1424-8220/19/21/4711autonomous vehiclesscene understandingocclusion reasoningroad detection |
| spellingShingle | Kewei Wang Fuwu Yan Bin Zou Luqi Tang Quan Yuan Chen Lv Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles Sensors autonomous vehicles scene understanding occlusion reasoning road detection |
| title | Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles |
| title_full | Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles |
| title_fullStr | Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles |
| title_full_unstemmed | Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles |
| title_short | Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles |
| title_sort | occlusion free road segmentation leveraging semantics for autonomous vehicles |
| topic | autonomous vehicles scene understanding occlusion reasoning road detection |
| url | https://www.mdpi.com/1424-8220/19/21/4711 |
| work_keys_str_mv | AT keweiwang occlusionfreeroadsegmentationleveragingsemanticsforautonomousvehicles AT fuwuyan occlusionfreeroadsegmentationleveragingsemanticsforautonomousvehicles AT binzou occlusionfreeroadsegmentationleveragingsemanticsforautonomousvehicles AT luqitang occlusionfreeroadsegmentationleveragingsemanticsforautonomousvehicles AT quanyuan occlusionfreeroadsegmentationleveragingsemanticsforautonomousvehicles AT chenlv occlusionfreeroadsegmentationleveragingsemanticsforautonomousvehicles |